SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2310.16045 · 2023

Woodpecker: Hallucination Correction for Multimodal Large Language Models

arXiv · PDF · Open in the Atlas

Code that ran

7 of 13 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 6 failures of our instrument; 6 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2310.16045.json · badge: /api/ran/2310.16045.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
bradyfu/woodpecker canonical (classifier label)
classifier basis: census
7 ran · 6 no recorded run
FunctionStatusWhere it lives
compute_iou Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
bradyfu/woodpecker/models/utils.py
pointer only (licence: NONE) · get_code("667ecbfb72739567")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, bradyfu/woodpecker when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

extract_boxes Ran
ran, honoured the contract we drafted
bradyfu/woodpecker/models/utils.py
pointer only (licence: NONE) · get_code("ded3d03af7363e20")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, bradyfu/woodpecker when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

find_matching_boxes Ran
ran; our contract draft was wrong, not the code
bradyfu/woodpecker/models/utils.py
pointer only (licence: NONE) · get_code("b5121592afbce3f8")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, bradyfu/woodpecker when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

format_inputs Ran
ran; our contract draft was wrong, not the code
bradyfu/woodpecker/models/claim_generator.py
pointer only (licence: NONE) · get_code("d1ffbb6af3208715")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, bradyfu/woodpecker when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_claim Ran
ran; our contract draft was wrong, not the code
bradyfu/woodpecker/models/claim_generator.py
pointer only (licence: NONE) · get_code("1e1856185896a734")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, bradyfu/woodpecker when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_res Ran
ran; our contract draft was wrong, not the code
bradyfu/woodpecker/models/questioner.py
pointer only (licence: NONE) · get_code("71e7ce8bf939f5d4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, bradyfu/woodpecker when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

remove_duplicates Ran
ran; our contract draft was wrong, not the code
bradyfu/woodpecker/models/questioner.py
pointer only (licence: NONE) · get_code("8a2ce3b99884243a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, bradyfu/woodpecker when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

find_most_similar_strings Not yet run
unverified (harvested, no recorded run)
bradyfu/woodpecker/models/detector.py
pointer only (licence: NONE) · get_code("9528b19eb2cc3b97")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, bradyfu/woodpecker when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

get_all_answers Not yet run
unverified (harvested, no recorded run)
bradyfu/woodpecker/models/answerer.py
pointer only (licence: NONE) · get_code("9698cd221b31fdd5")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, bradyfu/woodpecker when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

get_answer Not yet run
unverified (harvested, no recorded run)
bradyfu/woodpecker/models/answerer.py
pointer only (licence: NONE) · get_code("20117a653c8f40ac")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, bradyfu/woodpecker when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

get_output Not yet run
unverified (harvested, no recorded run)
bradyfu/woodpecker/models/preprocessor.py
pointer only (licence: NONE) · get_code("8122965ad6131653")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, bradyfu/woodpecker when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

get_output Not yet run
unverified (harvested, no recorded run)
bradyfu/woodpecker/models/refiner.py
pointer only (licence: NONE) · get_code("3cc2c9efff7e5609")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, bradyfu/woodpecker when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

get_res Not yet run
unverified (harvested, no recorded run)
bradyfu/woodpecker/models/entity_extractor.py
pointer only (licence: NONE) · get_code("8dbb0079cf7049ec")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, bradyfu/woodpecker when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 13 samples lifted from this paper's linked repositories, 13 carry a function identity and 0 do not. Of the 13 distinct functions with an identity, 9 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 9 later) and 4 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
format_inputs 2 other papers
2 later
2311.13614 (2023-11)
HalluciDoctor: Mitigating Hallucinatory Toxicity in Visual Instruction Data
2403.00425 (2024-03)
HALC: Object Hallucination Reduction via Adaptive Focal-Contrast Decoding
find_most_similar_strings 1 other paper
1 later
2403.00425 (2024-03)
HALC: Object Hallucination Reduction via Adaptive Focal-Contrast Decoding
get_all_answers 1 other paper
1 later
2403.00425 (2024-03)
HALC: Object Hallucination Reduction via Adaptive Focal-Contrast Decoding
get_claim 1 other paper
1 later
2403.00425 (2024-03)
HALC: Object Hallucination Reduction via Adaptive Focal-Contrast Decoding
get_output 1 other paper
1 later
2403.00425 (2024-03)
HALC: Object Hallucination Reduction via Adaptive Focal-Contrast Decoding
get_output 1 other paper
1 later
2403.00425 (2024-03)
HALC: Object Hallucination Reduction via Adaptive Focal-Contrast Decoding
get_res 1 other paper
1 later
2403.00425 (2024-03)
HALC: Object Hallucination Reduction via Adaptive Focal-Contrast Decoding
get_res 1 other paper
1 later
2403.00425 (2024-03)
HALC: Object Hallucination Reduction via Adaptive Focal-Contrast Decoding
remove_duplicates 1 other paper
1 later
2403.00425 (2024-03)
HALC: Object Hallucination Reduction via Adaptive Focal-Contrast Decoding

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Hallucination is a big shadow hanging over the rapidly evolving Multimodal Large Language Models (MLLMs), referring to the phenomenon that the generated text is inconsistent with the image content. In order to mitigate hallucinations, existing studies mainly resort to an instruction-tuning manner that requires retraining the models with specific data. In this paper, we pave a different way, introducing a training-free method named Woodpecker. Like a woodpecker heals trees, it picks out and corrects hallucinations from the generated text. Concretely, Woodpecker consists of five stages: key concept extraction, question formulation, visual knowledge validation, visual claim generation, and hallucination correction. Implemented in a post-remedy manner, Woodpecker can easily serve different MLLMs, while being interpretable by accessing intermediate outputs of the five stages. We evaluate Woodpecker both quantitatively and qualitatively and show the huge potential of this new paradigm. On the POPE benchmark, our method obtains a 30.66%/24.33% improvement in accuracy over the baseline MiniGPT-4/mPLUG-Owl. The source code is released at https://github.com/BradyFU/Woodpecker.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2310.16045")
get_code_for_paper("2310.16045")
have("2310.16045")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2310.16045.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2310.16045.svg)](https://syntology.ai/paper/2310.16045)

Connect an agent — have() is free.